Real-time Analytics
VinuesaLab needed high-fidelity, city-scale urban airflow simulation for planning and resilience work, but traditional CFD workflows were too slow, too resource intensive, and largely constrained to 2D approximations.
Reported impact
VinuesaLab achieved 10x faster training, progressed from 2D analysis to interactive 3D urban-flow simulations, and built a real-time emulator that supports data-driven planning for wind, pollution, and urban-heat resilience studies.
VinuesaLab built Diff-SPORT as an AI-driven urban-flow framework on NVIDIA PhysicsNeMo so the team could move from slow, 2D turbulence studies to scalable 3D reconstruction and real-time environmental emulation. The system combines generative models, physics-informed machine learning, and computational fluid-dynamics knowledge to reconstruct wind behavior, pollutant hotspots, and temperature changes across complex city layouts. RTX GPU acceleration speeds local training and experimentation, while an NVIDIA Academic Grant supplied A100 Tensor Core GPUs and 16,000 compute hours for larger runs and multi-node scaling. Because PhysicsNeMo supports distributed execution, the team can train on larger domains, integrate real city layouts, and reuse the same framework for collaborations in Europe and the United States instead of rebuilding separate simulation stacks for each deployment.
Urban geometry, CFD context, and sensor observations are fed into Diff-SPORT on top of PhysicsNeMo, where GPU-accelerated training learns 3D flow reconstructions and real-time emulators. The resulting models generate wind, pollution, and temperature predictions that planners can visualize and test across full metropolitan layouts.
Achieved a tenfold speedup in model training using NVIDIA PhysicsNeMo and RTX GPU acceleration, reducing processing time from hours to seconds.
Developed a real-time emulator capable of visualizing wind patterns, pollutant hotspots, and temperature changes.
NVIDIA has continued to support this project through the NVIDIA Academic Grant Program, which awarded the team eight NVIDIA A100 Tensor Core GPUs, accessed through 16,000 compute hours.
We recognized that GPU acceleration was essential to make high-resolution 3D urban flow reconstruction practical, rather than purely theoretical.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample May 5, 2026 Colorado State University Colorado State University needed a practical way to forecast severe hailstorms earlier and across multiple radar systems, but traditional nowcasting approaches were largely limited to 30- to 60-minute windows and… 2-3-hour lead time Earth2Studio · NVIDIA Earth-2 StormScope · NVIDIA H100 and A100 GPUs NVIDIA Sample Oct 9, 2026 California Department of Transportation (Caltrans) Caltrans needed to inspect and monitor roughly 1,200 active transportation projects more frequently and safely, but manual site visits were slow, inconsistent, and risky for staff working around traffic, bridges, and… Remote operations up to 100 miles Esri ArcGIS · NVIDIA CUDA · NVIDIA Jetson Orin NVIDIA Sample Sep 30, 2026 EPRI EPRI needed to run advanced AI for sensitive utility documents and weather-planning workflows locally, because energy-sector research data could not leave controlled environments and shared compute delays limited how… 150 tokens/sec aggregate across 10 concurrent Power Chat users DGX Spark · Dell Pro Max with GB10 · NVIDIA CBottle 